Date: Thu, 10 Nov 2016 12:37:05 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Mark Rutland <mark.rutland@arm.com>
Cc: kan.liang@intel.com, mingo@redhat.com, linux-kernel@vger.kernel.org,
        acme@kernel.org, tglx@linutronix.de,
        alexander.shishkin@linux.intel.com, vince@deater.net,
        eranian@google.com, andi@firstfloor.org
Subject: Re: [PATCH] perf/core: introduce context per CPU event list
Message-ID: <20161110113704.GU3142@twins.programming.kicks-ass.net>
References: <1478718286-12824-1-git-send-email-kan.liang@intel.com>
 <20161110083355.GO3568@worktop.programming.kicks-ass.net>
 <20161110110516.GA4418@leverpostej>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20161110110516.GA4418@leverpostej>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1446
Lines: 31

On Thu, Nov 10, 2016 at 11:05:17AM +0000, Mark Rutland wrote:
> Hi,
> 
> On Thu, Nov 10, 2016 at 09:33:55AM +0100, Peter Zijlstra wrote:
> > Yes this is a problem, but no this cannot be done. We can't have per-cpu
> > storage per task. That rapidly explodes.
> > 
> > Mark is looking at replacing this stuff with an rb-tree for big-little,
> > that would also allow improving this I think.
> 
> Unfortunately I've not had the chance to look at that since returning
> from Plumbers. Also, I was leaning towards the alternative approach we
> discussed, with a perf_event_task_contexts container, as that also
> solved some other issues with the way we used perf_event_context::pmu in
> big.LITTLE systems.
> 
> Looking at the way perf_iterate_ctx is used, it seems that we're just
> trying to iterate over the active events for a context (i.e. those
> programmed into the HW at this point in time). Though I'm missing some
> subtlety, since we check event->state < PERF_EVENT_STATE_INACTIVE.
> 
> We have a similar issue with perf_event_task_tick() needing to know the
> relevant contexts, and for that we have the active_ctx_list. Can't we do
> something similar and add an active_events_list to perf_event_context?

So the problem is finding which events are active when.

If we stick all events in an RB-tree sorted on: {pmu,cpu,runtime} we
can, fairly easily, find the relevant subtree and limit the iteration.
Esp. if we use a threaded tree.